by PerplexityReleased 7 March 2025
Perplexity's enterprise search model for questions that take several searches to answer, citing about twice as many sources per search as Sonar and holding more context for long follow-up threads
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 998,51 DA | 4 992,53 DA |
per 1M tokens
Web search · 1,66 DA per call
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Latency | Throughput | Uptime |
|---|---|---|---|---|---|
| Perplexity | 998,51 DA | 4 992,53 DA | … | … | … |
Also charged: a web search 1,66 DA each.
You pay the price of the provider that served your request. Prices read 15:18 · speed over the last 30 minutes · uptime over 3 days.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTwo lines to welcome a shop in Oran.
Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.
Try in Chat LabTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://opendunes.com/v1",
api_key=os.environ["OPENDUNES_API_KEY"],
)
resp = client.chat.completions.create(
model="perplexity/sonar-pro",
messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)
print(resp.choices[0].message.content)Runs this request once on your balance.
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
Shaping the reply
How long, how varied, where to stop.
max_tokenstemperaturetop_ptop_kfrequency_penaltypresence_penaltyOther
Also accepted by this model.
web_search_optionsAbout 5,16 DA per message. ↑ 998,51 DA · ↓ 4 992,53 DA per 1M tokens · 1,66 DA per request.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Perplexity's enterprise search model for questions that take several searches to answer, citing about twice as many sources per search as Sonar and holding more context for long follow-up threads.
Sonar Pro Search costs 4,33 DA more for the same message.
Deposit dinars with your Edahabia or CIB card. Every model, Sonar Pro included, is paid from that balance. No foreign card, no conversion.
Perplexity names no languages for Sonar Pro. Arabic, French and Darja: not stated.
It reads text and images. Up to 200K tokens in one request, about 200 pages. It writes up to 6 000 words at once.
No. Perplexity has not published its weights.
Perplexity. Released 7 March 2025.
Decider V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions of three kinds: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns the probability of every answer, so your own system sets its thresholds for sorting, routing or moderation. It is the larger model of the pair and reads about 262 pages; Decider Flash V1.2 is the smaller, lower-cost version.
Embed V1 0.6B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 1,024 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the small, quick model of the pair.
Embed V1 4B turns text of up to about 32 pages into a fingerprint of its meaning, a list of 2,560 numbers, so search finds text that means the same thing. It needs no special instruction before the text and is built for large-scale search over independent texts, search queries and single sentences. It is the larger model of the pair, tuned for the best result quality.
Decider Flash V1.2 does not write text. You send content as text, a table of data or a picture, plus named questions: yes or no, a choice among as many as 255 options, or a score on an ordered scale. It returns a probability for every answer, so your own system sets its thresholds for sorting, routing or moderating high volumes.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first No.
Works through the problem before it answers.
Uses your tools No.
Can call functions your code provides.
Fills your JSON No.
Answers in the JSON shape you give it.
Searches the web
Can look things up online while it answers.
Cheaper on repeats No.
A prompt it saw a moment ago costs less the second time.
Open weights No.
Read on docs.perplexity.ai.
Compare two products using current reviews
Searches the web
Answer a detailed question about recent news with sources
Searches the web
Research a topic across many sources and summarise
Searches the web